JP2019139521A - Prediction device, prediction method, and prediction program - Google Patents

Abstract

To provide a prediction device, a prediction method, and a prediction program for appropriately predicting the promising degree regarding the future by using an evaluation value (score) in a company indicating how active an action subject is in a company or the like, namely, how useful a human resource is.SOLUTION: A prediction device comprises: an acquisition unit configured to acquire action information indicating a history of actions by a predetermined action subject; and a prediction unit configured to predict a promising degree related to the future of the predetermined action subject at a time point later than the action on the basis of the action information acquired by the acquisition unit.SELECTED DRAWING: Figure 4

Description

  The present invention relates to a prediction device, a prediction method, and a prediction program.

  2. Description of the Related Art Conventionally, various techniques relating to identification and prediction of the appropriateness of a subject (behavior subject) who performs a user's behavior have been provided. For example, providing a task to the target person (user), evaluating the characteristics of the target based on the performance value indicated by the target in the execution of the task, and based on the evaluated characteristics, the target is hired by the entity Techniques are provided to identify suitability.

JP-T-2017-522676

  However, in the above-described conventional technology, it may be difficult to appropriately predict the promising degree of the action subject. For example, only the evaluation based on the execution of the task provided to the target person (user) merely evaluates the user at the time of execution of the task, and it is difficult to predict the promising degree regarding the future of the user.

  The present application has been made in view of the above, and an object thereof is to provide a prediction device, a prediction method, and a prediction program that appropriately predict the promising degree of an action subject.

  The prediction device according to the present application includes an acquisition unit that acquires behavior information indicating a history of behavior by a predetermined behavior subject, and the predetermined information at a time point later than the behavior based on the behavior information acquired by the acquisition unit. And a predicting unit for predicting the promising degree related to the future of the action subject.

  According to one aspect of the embodiment, there is an effect that the promising degree of the action subject can be appropriately predicted.

FIG. 1 is a diagram illustrating an example of a generation process according to the embodiment. FIG. 2 is a diagram illustrating an example of a prediction process according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of the prediction system according to the embodiment. FIG. 4 is a diagram illustrating a configuration example of the prediction device according to the embodiment. FIG. 5 is a diagram illustrating an example of a learning data storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of the model information storage unit according to the embodiment. FIG. 7 is a diagram illustrating an example of a user information storage unit according to the embodiment. FIG. 8 is a diagram illustrating an example of the promising degree information storage unit according to the embodiment. FIG. 9 is a diagram illustrating an example of the prediction information storage unit according to the embodiment. FIG. 10 is a flowchart illustrating an example of the generation process according to the embodiment. FIG. 11 is a flowchart illustrating an example of the prediction process according to the embodiment. FIG. 12 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the prediction device.

  Hereinafter, modes for carrying out a prediction apparatus, a prediction method, and a prediction program according to the present application (hereinafter referred to as “embodiments”) will be described in detail with reference to the drawings. Note that the prediction device, the prediction method, and the prediction program according to the present application are not limited to the embodiment. In the following embodiments, the same portions are denoted by the same reference numerals, and redundant description is omitted.

(Embodiment)
[1. Generation process)
First, an example of the generation process according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of a generation process according to the embodiment. In the example of FIG. 1, the case where a user is an action subject is shown as an example. The action subject is not limited to the user as long as it is the subject that performs the action, and may be various subjects such as a predetermined group such as a school or a corporation. FIG. 1 illustrates a case where the prediction apparatus 100 generates a model based on data including user behavior information and correct information indicating a job title of the organization to which the user belongs. In the example of FIG. 1, the prediction device 100 displays a history of each user's behavior up to year X (for example, 2010) and a score corresponding to the post of the user from year X to year Y (for example, five years later). A case where a model is generated based on data including correct answer information is shown. The prediction target is not limited to the user's job title, but may be any information. For example, the prediction target may be an evaluation value (score) or the like in the company indicating how active the user is in the company or the like, that is, how useful the human resource is. For example, the evaluation value in the company may be personnel evaluation, sales results, awards in the company, research results, the number of papers, the number of patents, and the like. Specifically, the evaluation value within the company is the score corresponding to each rank of personnel evaluation, sales performance, and research performance, the score according to the number of awards in the company, the score according to the number of papers, and the number of patents. It may be a score based on various in-house evaluations such as a corresponding score. Hereinafter, data including user behavior information and correct information associated with the behavior information is also referred to as “learning data”. User behavior information will be described later.

  Moreover, the prediction apparatus 100 predicts the promising degree of the user based on the behavior information of a certain user using the generated model. Further, the prediction device 100 provides a service based on information indicating the predicted degree of promising action subject. This point will be described with reference to FIG.

[Configuration of prediction system]
First, prior to the description of FIG. 1, the prediction system 1 shown in FIG. 3 will be described. As illustrated in FIG. 3, the prediction system 1 includes a terminal device 10 and a prediction device 100. The terminal device 10 and the prediction device 100 are connected via a predetermined network N so as to be communicable by wire or wirelessly. FIG. 3 is a diagram illustrating a configuration example of the prediction system according to the embodiment. Note that the prediction system 1 illustrated in FIG. 3 may include a plurality of terminal devices 10 and a plurality of prediction devices 100.

  The terminal device 10 is an information processing device used by a user. The terminal device 10 is realized by, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. In the example shown in FIG. 1, the case where the terminal device 10 is a smartphone used by the user is shown. Hereinafter, the terminal device 10 may be referred to as a user. That is, hereinafter, the user can be read as the terminal device 10. For example, FIG. 2 shows a case where the terminal device 10 is a smartphone used by the user U1. Note that, as described above, “user U * (* is an arbitrary numerical value)” indicates that the user is a user identified by the user ID “U *”. For example, when “user U1” is described, the user is a user identified by the user ID “U1”.

  The terminal device 10 may collect user behavior information and transmit it to the prediction device 100. The terminal device 10 may have a function such as a GPS (Global Positioning System) sensor, and may detect and acquire user position information (sensor information). Moreover, the terminal device 10 may detect various sensor information not only with a GPS sensor etc. but with various sensors. For example, the terminal device 10 may predict and acquire the position information of the user using the position information of the base station with which communication is performed or the radio wave of WiFi (registered trademark) (Wireless Fidelity). Moreover, the terminal device 10 has a function of an acceleration sensor, and may detect and acquire acceleration information (sensor information) in the movement of the user. Further, the terminal device 10 may have various functions such as a temperature sensor and an atmospheric pressure sensor, and may be able to detect and acquire environmental information where the user is placed such as temperature and atmospheric pressure. Moreover, the terminal device 10 may have various functions such as a heart rate sensor, and may be able to detect and acquire a user's biological information. For example, a user using the terminal device 10 may acquire a user's own context information by the terminal device 10 by wearing a wearable device that can communicate with the terminal device 10. For example, a user who uses the terminal device 10 wears a wristband type wearable device that can communicate with the terminal device 10, and the terminal device 10 acquires information on the user's own heartbeat (pulse) by the terminal device 10. It may be possible.

  The prediction device 100 is an information processing device that predicts the promising degree of an action subject based on user action information. In the example of FIG. 2, the prediction device 100 is a model used for predicting the promising degree of the action subject, and predicts the promising degree of the action subject based on the output of the model to which the user behavior information is input. For example, the prediction device 100 acquires user behavior information from the terminal device 10 used by the user. Further, for example, the prediction device 100 may acquire user behavior information from another information processing device that collects user behavior information.

  Moreover, the prediction apparatus 100 provides a service based on the information regarding the predicted degree of promising action subject. For example, the prediction device 100 may provide information indicating the promising degree of the action subject to an organization (organization) such as a company to which the user belongs or a company that the user desires to belong to. In the example of FIG. 2, the prediction apparatus 100 provides information indicating the promising degree of the position of the user U1 to a company in which the promising degree of the position of the user U1 is undergoing the employment test. Note that the prediction device 100 may provide information indicating the promising degree of the action subject to the business entity to which the user belongs.

  First, in the example illustrated in FIG. 1, the learning data LD1 used by the prediction device 100 for generating the model M1 will be described. In the example of FIG. 1, as shown in the position group POS, one of the four positions of the A position, the B position, the C position, and the D position will be described as an example. In the example of FIG. 1, the position A is the director with the highest rank, the position B is the general manager whose rank is the next higher rank, and the position C is the rank with the next highest rank. This is a case where the section manager is D and the position D is the position having the lowest rank and has no position.

  For example, the prediction apparatus 100 associates higher scores with higher ranks. For example, as shown in the rank list RL11 (see FIG. 2), the prediction device 100 associates the highest score “1” with the A title (director), and associates the score “0.6” with the B title (director). The score “0.3” is associated with the position C (section manager), and the lowest score “0” is associated with the position D (none). For example, the prediction apparatus 100 stores in the storage unit 120 information in which positions and scores are associated with each other as shown in the rank list RL11. Note that the associations with positions and scores as described above are examples, and the prediction apparatus 100 may use associations of scores with various positions and positions.

  In the example of FIG. 1, the prediction device 100 acquires the behavior information of each user as shown in the behavior group AC. For example, the learning data LD1 includes data DT101 including behavior information ADT101 collected for the user U101 and correct information RDT101 indicating the post of the user U101. In the example of FIG. 1, the user U101 has a job title A (director) after year Y from year X, and the correct answer information RDT101 includes a job title of user U101 as job title A (director). Information indicating that the score is “1” is included.

  For example, the prediction device 100 acquires the behavior information ADT101 from the terminal device 10 used by the user U101. For example, the prediction device 100 acquires behavior information ADT101 including a history of various behaviors such as search, content browsing, and purchase by the user U101. For example, the prediction apparatus 100 uses the behavior information ADT101 of the user U101 in the year X and the correct information RDT101 indicating the post of the user U101 Y years after the year X as learning data. For example, the prediction apparatus 100 uses, as learning data, the behavior information ADT101 of the user U101 in the year 2010, which is the year X, and the correct answer information RDT101 indicating the post of the user U101 in 2015 five years after 2010.

  As described above, when “data DT * (* is an arbitrary numerical value)” is described, it indicates that the data is data identified by the data ID “DT *”. For example, when “data DT1” is described, the data is data identified by the data ID “DT1”.

  The user behavior information here includes various information related to the user behavior. For example, as shown in the behavior information ADT101, the user U101 is a user whose history of various behaviors such as search, content browsing, and purchase of the user U1 up to year X (for example, 2010) is collected. Show. The user behavior information is not limited to the above, and may include various behavior histories.

  For example, the learning data LD1 includes data DT102 including behavior information ATD102 collected for the user U102 and correct information RDT102 corresponding to the user U102. In the example of FIG. 1, the user U102 has a job title D (none) after year Y from year X, and the correct information RDT102 includes a job title D (none) in the user U102. Information indicating that the score is “0” is included.

  For example, the prediction device 100 acquires the behavior information ADT102 from the terminal device 10 used by the user U102. For example, the prediction device 100 acquires behavior information ADT102 including a history of various behaviors such as search, content browsing, and purchase by the user U102. For example, the prediction device 100 uses, as learning data, the behavior information ADT102 of the user U102 in the year X and the correct information RDT102 indicating the post of the user U102 Y years after the year X. For example, the prediction apparatus 100 uses, as learning data, the behavior information ADT102 of the user U102 in 2010, which is the year X, and the correct answer information RDT102 indicating the post of the user U102 in 2015 five years after 2010.

  The learning data LD1 includes action information ATD103 collected for the user U103, data DT103 including correct answer information RDT103 corresponding to the user U103, data DT104 including action information ATD104 collected for the user U104, and the like. For example, the prediction device 100 acquires the behavior information ATD103 from the terminal device 10 used by the user U103. For example, the prediction device 100 acquires the behavior information ATD104 from the terminal device 10 used by the user U104.

  In FIG. 1, only the data DT101 to DT104 are illustrated, but the learning data LD1 includes a large number of data. For example, the prediction apparatus 100 acquires the title of each user from a company or the like to which each user belongs. For example, the users U101 to U104 may be users who belong to the company CP11 that is the information providing destination in FIG. For example, the users U101 to U104 may be users who belong to companies other than the company CP11.

  For example, the prediction device 100 may generate correct information RDT101 to RDT104 and the like based on information indicating the positions of the users U101 to U104. Further, for example, the prediction device 100 may acquire the correct information RDT101 to RDT104 of each user U101 to U104 from a company to which each user belongs, another information processing device, or the like. Moreover, the prediction apparatus 100 may acquire action information of each user from an external device other than the terminal device 10 used by the user.

  From here, each process of the prediction apparatus 100 is demonstrated. First, the prediction device 100 acquires learning data LD1 (step S11). Specifically, the prediction device 100 acquires learning data LD1 including data DT101 to DT104 and the like. In the example of FIG. 1, the prediction device 100 may acquire the learning data LD1 as described above from a predetermined external information processing device.

  And the prediction apparatus 100 adds the combination of the correct information contained in the learning data LD1 acquired by step S11, and a user's action information as learning data (step S12). Specifically, the prediction device 100 adds the learning data LD1 to the learning data storage unit 121.

  And the prediction apparatus 100 produces | generates a model based on learning data (step S13). In the example of FIG. 1, the prediction device 100 generates a model M1 as shown in the model list ML11. As described above, when “model M * (* is an arbitrary numerical value)” is described, it indicates that the model is a model identified by the model ID “M *”. For example, when “model M1” is described, the model is a model identified by the model ID “M1”. For example, the prediction device 100 stores information on the model M1 as shown in the model list ML11 in the model information storage unit 122 (see FIG. 6).

  As shown in the model list ML11 in FIG. 1, the model M1 indicates that the model is used for predicting the promising degree when the action subject is a user. The model M1 indicates that the prediction target is a promising degree “position (promoting prospective degree)”, that is, a model used for predicting the promising degree of promotion of a user who is an action subject. The model M1 indicates that the specific model data is “model data MDT1”.

  For example, the prediction device 100 generates a model by performing learning using the data DT101 to DT104 in the learning data storage unit 121 as learning data (teacher data). For example, the prediction device 100 generates a model using a feature amount related to user behavior information. For example, the prediction device 100 generates a model using the feature amount related to the behavior information corresponding to the search by the user. For example, the prediction device 100 generates a model using a feature amount related to a query used by a user for a search. In addition, for example, the prediction device 100 generates a model using a feature amount related to behavior information corresponding to content browsing by a user. For example, the prediction device 100 generates a model using a feature amount related to content browsed by the user. In addition, for example, the prediction device 100 generates a model using a feature amount related to behavior information corresponding to purchase by a user. For example, the prediction device 100 generates a model using feature quantities related to products and services purchased by the user.

  As described above, the prediction device 100 learns features corresponding to the user's behavior and generates a model that predicts the promising degree of the user who is the subject of the behavior. In the example of FIG. 1, the prediction device 100 learns features related to user behavior information and generates a model for predicting the promising degree of the behavior subject. The feature corresponding to the user that the prediction device 100 learns may be input to the prediction device 100 by a person such as an administrator of the prediction device 100 or may be automatically learned (extracted) by the prediction device 100. Good.

  For example, the prediction device 100 generates a model M1 using the learning data LD1. For example, in the prediction apparatus 100, since the post of the user U101 included in the correct answer information RDT101 is the A post (director) and the score is “1”, the user behavior information ADT101 included in the data DT101 is input to the model M1. In such a case, the learning process is performed so that the score output by the model M1 approaches “1”. For example, when the behavior information ADT101 of the data DT101 is input to the model M1, the prediction device 100 performs a learning process so that the score output by the model M1 approaches “1”.

  Further, for example, the prediction device 100 includes the user's action information ADT102 included in the data DT102 in the model M1 because the position of the user U102 included in the correct answer information RDT102 is the D position (none) and the score is “0”. Is input so that the score output by the model M1 approaches “0”. For example, when the behavior information ADT102 of the data DT102 is input to the model M1, the prediction device 100 performs a learning process so that the score output by the model M1 approaches “0”.

  Further, for example, the prediction apparatus 100 has the user's U103 job title included in the correct answer information RDT103 as the job title C (section manager) and the score is “0.3”. When the information ADT 103 is input, the learning process is performed so that the score output by the model M1 approaches “0.3”. For example, when the behavior information ADT103 of the data DT103 is input to the model M1, the prediction device 100 performs a learning process so that the score output by the model M1 approaches “0.3”.

  In addition, for example, the prediction apparatus 100 has the user U104's post included in the correct answer information RDT104 as the B post (department manager) and the score is “0.6”, and thus the user's action included in the data DT104 in the model M1 When the information ADT 104 is input, the learning process is performed so that the score output by the model M1 approaches “0.6”. For example, when the behavior information ADT104 of the data DT104 is input to the model M1, the prediction device 100 performs a learning process so that the score output by the model M1 approaches “0.6”.

  Note that the model learning technique is not limited to the technique described above, and any known technique can be applied. Each model may be generated using various conventional techniques relating to machine learning as appropriate. For example, the model generation may be performed using a technique related to machine learning of supervised learning such as SVM (Support Vector Machine). Further, for example, the model generation may be performed using a technique related to machine learning of unsupervised learning. For example, the generation of the model may be performed using a deep learning technique. For example, the model generation may be performed by appropriately using various deep learning techniques such as DNN (Deep Neural Network), RNN (Recurrent Neural Network), and CNN (Convolutional Neural Network). The description relating to the generation of the model is merely an example, and the generation of the model may be performed by a learning method appropriately selected according to information that can be acquired. That is, the prediction device 100 can use any method for the model M1 as long as it can learn the model M1 so as to output a score corresponding to the correct answer information when user behavior information included in the learning data is input. May be generated.

  Through the processing as described above, the prediction device 100 generates a model M1 corresponding to the promising degree regarding the post. For example, the prediction device 100 causes the model M1 to output a score indicating the degree of promising future positions (promotions) for the user corresponding to the input user behavior information by inputting the user behavior information to the model M1. Based on the score output from the model M1, the promising degree of the position of the user is predicted. Thus, the prediction device 100 predicts the future activity of the user based on the score output by the model M1. For example, the prediction device 100 predicts how much the user will be active in the company or society based on the score output by the model M1.

  As described above, the prediction device 100 makes it possible to appropriately predict the promising degree related to a certain user's position by learning using learning data in which the user's behavior information and correct information regarding the position are associated with each other. A model can be generated. Therefore, the prediction apparatus 100 accurately predicts the promising degree of the future whether a certain user plays an active role in an organization (company) and is promoted by using the model generated as described above. Is possible.

[2. (Prediction process)
An example of the prediction process according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating an example of a prediction process according to the embodiment. In FIG. 2, the prediction apparatus 100 shows the case where the user U1's behavior information is given, predicting the promising degree of the user U1, and providing information based on the prediction.

  First, the prediction device 100 acquires action information ADT1 of the user U1 (step S21). In the example of FIG. 2, the prediction device 100 acquires the behavior information ADT1 of the user U1 from the terminal device 10 used by the user U1. For example, the prediction device 100 acquires action information ADT1 including a history of various actions such as search, content browsing, and purchase by the user U1. For example, the prediction device 100 acquires the behavior information ADT1 of the user U1 up to year Z. For example, the prediction device 100 acquires the behavior information ADT1 of the user U1 in the year Z. For example, the prediction device 100 acquires the behavior information ADT1 of the user U1 in the year 2017, which is the year Z.

  For example, the prediction apparatus 100 predicts the promising degree of the post of 2022 in 2022 five years from 2017, using the behavior information ADT1 of the user U1 and the model M1 in the year of 2017. The prediction device 100 that has acquired the behavior information ADT1 inputs the behavior information ADT1 into the model. For example, the prediction device 100 inputs the behavior information ADT1 of the user U1 to the model M1.

  In the example of FIG. 2, the prediction device 100 generates (calculates) a score indicating the degree of promising degree of the prediction target “position” of the user U <b> 1 by processing as illustrated in the processing group PS <b> 22-1. The prediction apparatus 100 inputs the action information of the user U1 who is the action subject to the model M1 corresponding to the prediction target “position (promotion degree of promotion)” (step S22-1). Specifically, the prediction device 100 inputs the behavior information ADT1 to the model M1. The model M1 to which the behavior information ADT1 is input outputs a score (step S23-1). In the example of FIG. 2, the model M1 to which the behavior information ADT1 is input outputs a score “0.7” as indicated by the score SC11-1.

  Then, the prediction device 100 predicts the promising degree of the user U1 based on the score output by the model M1 (step S24). For example, the prediction device 100 generates the prediction information PL11 based on the prediction of the promising degree of the user U1. In the example of FIG. 2, the prediction device 100 predicts the promising degree of the user U <b> 1 based on the score output by the model M <b> 1 and the information stored in the promising degree information storage unit 124. The prediction apparatus 100 is based on the information (sometimes referred to as “association information”) in which the score and the degree of hope are associated with each other as shown in the degree-of-probability information storage unit 124 in FIG. Predict the degree.

  The promising degree information storage unit 124 illustrated in FIG. 2 includes items such as “score” and “promising degree”. The “score” indicates a score value (range) corresponding to the corresponding promising degree. “Promising degree” indicates the level of the promising degree of the action subject when the score of the action subject is a corresponding score. In the example of FIG. 2, “promising degree” corresponds to three score ranges, and shows three levels of “low”, “medium”, and “high”. For example, the association information in the promising degree information storage unit 124 illustrated in FIG. 2 indicates that the promising degree of the user is “low” when the score of the user who is the action subject is less than 0.3. The association information in the promising degree information storage unit 124 shown in FIG. 2 indicates that the promising degree of the user is “medium” when the user's score is 0.3 or more and less than 0.6. Further, the association information in the promising degree information storage unit 124 shown in FIG. 2 indicates that the promising degree of the user is “high” when the user's score is 0.6 or more.

  The prediction apparatus 100 compares the score output by the model M1 with the score range of the association information in the promising degree information storage unit 124 illustrated in FIG. 2, and the score output by the model M1 is in any score range. Determine whether it is included. In the example of FIG. 2, the prediction device 100 determines that the score output by the model M1 is “0.7”, and the promising degree corresponds to a score “0.6 or more” corresponding to “high”. Therefore, as shown in the prediction information PL11, the prediction device 100 predicts that the promising degree corresponding to the prediction target “post (promotion degree of promotion)” of the user U1 is “high”.

  Moreover, the prediction apparatus 100 predicts the post of the user U1 after Y years from Z years using the rank list RL11. The rank list RL11 illustrated in FIG. 2 includes information in which the highest score “1” is associated with the A title (director) and the score “0.6” is associated with the B title (director). Further, in the rank list RL11 shown in FIG. 2, information (promotion) in which the score “0.3” is associated with the C position (section manager) and the lowest score “0” is associated with the position D (none). Information). For example, the prediction device 100 acquires information that associates the post and the score as shown in the rank list RL11 from the storage unit 120.

  Then, the prediction device 100 compares the score output by the model M1 with the score of the promotion information in the rank list RL11 illustrated in FIG. 2, and determines which score is higher than the score output by the model M1. In the example of FIG. 2, the prediction apparatus 100 has a score “0.7” output from the model M1, a score of “0.6” or more for the B title (director), and a score “0.6” for the A title (director). It is determined that it is less than 1 ”. Therefore, as shown in the prediction information PL11, the prediction device 100 predicts the position of the user U1 in the prediction target “position (promotion degree of promotion)” as “over manager”. For example, the prediction apparatus 100 predicts the post of the user U1 after Y years from Z years as “director or higher”. In this case, the prediction device 100 predicts that the user U1 is promoted to a position higher than the general manager after the year Y from the year Z. For example, the prediction device 100 predicts that the user U1 is promoted to a position higher than the general manager in 2022, five years after 2017.

  Thereafter, the prediction device 100 provides information based on the predicted promising degree of the action subject (step S25). In the example of FIG. 2, the prediction device 100 provides the prediction information PL <b> 11 of the user U <b> 1 to a company that desires information regarding the degree of promising user U <b> 1. In the example of FIG. 2, the prediction device 100 provides the prediction information PL11 of the user U1 to the operator terminal 20 used by the manager MA1 of the company CP11 that the user U1 has undergone the employment test. The manager MA1 may be a personnel manager of the company CP11. FIG. 2 shows a case where the operator terminal 20 used by the manager MA1 of the company CP11 that is the information providing destination is a notebook computer. The business entity terminal 20 may be an information processing device similar to the terminal device 10. The prediction device 100 transmits the prediction information PL11 of the user U1 to the operator terminal 20 used by the manager MA1. Then, the business entity terminal 20 that has received the prediction information PL11 from the prediction device 100 displays the prediction information PL11. Thereby, manager MA1 of company CP11 confirms the promising degree of the post of user U1.

  Note that the manager MA1 of the company CP11 may request the prediction device 100 for information regarding the promising degree of the position of the user U1. In this case, the prediction device 100 may transmit the prediction information PL11 to the operator terminal 20 in response to a request for information regarding the degree of hope of the user U1 from the operator terminal 20 used by the manager MA1.

  As described above, the prediction device 100 predicts the promising degree of the action subject based on the user action information. In the example of FIG. 2, the prediction device 100 outputs a score related to the promising degree of the prediction target “position” corresponding to the model M1 by inputting the behavior information ADT101 of the user U1 to the model M1. Then, the prediction device 100 predicts that the higher the score output by the model, the higher (larger) the user's promising degree regarding the prediction target corresponding to the model. Then, the prediction device 100 provides the generated prediction information PL11 to the operator terminal 20 used by the administrator MA1 of the company CP11 in which the user U1 is undergoing the employment test. As described above, the prediction device 100 predicts the promising degree of the action subject, and transmits the information related to the predicted promising degree of the action subject to the provider having a relationship with the action subject. As a result, the provider receiving the information from the prediction device 100 can appropriately grasp the promising degree of the action subject.

(2-1. Action subject, prediction target)
In the example of FIG. 1 and FIG. 2, the job title in the organization to which the user belongs is shown as a prospective target, that is, a user's promotion prospective prediction target. There may be. For example, the action subject may be a predetermined corporation or a predetermined group.

  For example, the prediction target of the promising degree may be any prediction target as long as it is an object indicating the future potential of the action subject. For example, the prediction target of the promising degree may be an object indicating the future such as social activity of the action subject. For example, when the action subject is a user, the prediction target of the promising degree may be a promising degree that the user starts a business and plays an active role (success), that is, a successful promising degree of starting a business. For example, when the action subject is a corporation such as a company, the prediction target of the promising degree may be a promising degree that the performance of the corporation increases, that is, a business promising degree or the like.

(2-2. About behavior information)
In the example of FIGS. 1 and 2, information corresponding to search, content browsing, and purchase has been described as an example of user behavior information in order to simplify the description. However, various information is included in the user behavior information. May be included. For example, the prediction device 100 may use not only user behavior on the Internet (web) but also various user behavior information that can be acquired. For example, the prediction device 100 may predict the promising degree using user behavior information including user behavior information in real space.

  For example, the prediction device 100 may predict the promising degree using user behavior information including post information posted by a user in a predetermined service. For example, the prediction device 100 may predict the promising degree using user behavior information including post information posted by the user in the SNS. For example, the prediction device 100 may predict the promising degree using user behavior information including post information posted by the user in Twitter (registered trademark), Facebook (registered trademark), or the like. For example, the prediction device 100 may predict the promising degree using user behavior information including character information posted by the user on Twitter. For example, the prediction device 100 may predict the promising degree using user behavior information including information input by the user in the message service. For example, the prediction apparatus 100 may predict the promising degree using user behavior information including information input by a user in a message service such as LINE (registered trademark). For example, the prediction device 100 may predict the promising degree using user behavior information including information input in an e-mail. In addition, for example, the prediction device 100 is promising by using user behavior information including various information such as character information, audio information, image information, and moving image information (video) as long as the information is input by the user. The degree may be predicted.

(2-3. About the model)
The generation of the model is not limited to that shown in FIG. Although the example of FIG. 1 shows a case where a plurality of models corresponding to each promising degree is generated, the prediction device 100 may generate one model that outputs a plurality of scores corresponding to each prediction target.

  In the example of FIG. 1, search, content browsing, and purchase are described as examples of user behavior information. However, the prediction device 100 generates a model using user behavior information including various information as input information. Also good.

  For example, the prediction device 100 may generate a model that uses, as input information, user action information including post information posted by a user in a predetermined service. For example, the prediction device 100 may generate a model using, as input information, user behavior information including post information posted by the user in a social networking service (SNS). For example, the prediction device 100 may generate a model that uses, as input information, user behavior information including post information posted by the user on Twitter, Facebook, or the like. For example, the prediction device 100 may generate a model that uses, as input information, user behavior information including character information posted by the user on Twitter. For example, the prediction device 100 may generate a model that uses user behavior information including information input by the user in the message service as input information. For example, the prediction device 100 may generate a model that uses user behavior information including information input by the user in a message service such as LINE as input information. For example, the prediction device 100 may generate a model that uses, as input information, user behavior information including information input in an e-mail. Further, for example, if the prediction device 100 is information input by the user, the user action information including various information such as character information, audio information, image information, and moving image information (video) is input information. A model to be generated may be generated.

(2-4. Prediction method)
In addition, although the example of FIG. 2 showed the case where it predicted using a model, you may predict a user's promising degree without using a model. For example, the prediction device 100 predicts the user's promising degree by determining whether the user's action satisfies the condition using a condition (also referred to as “promising condition”) indicating that the user is promising. May be. That is, the prediction apparatus 100 may predict the user's promising degree by determining whether or not the user's action meets the promising condition. For example, when the prediction device 100 determines that the user's action corresponds to the promising condition, the prediction device 100 may predict the user with the promising degree “high”. In addition, for example, when the prediction device 100 determines that the user's action does not correspond to the promising condition, the prediction device 100 may predict the user as having a low promising degree.

  For example, the prediction device 100 may predict the promising degree of the user as “high” when the user concentrates on activities related to academic work or work during a predetermined period (for example, one month). . For example, when the ratio of the position information of the user corresponding to the position of the university in the last three months until graduation from the university is equal to or higher than a predetermined threshold (for example, 50%), for example, the prediction apparatus 100 determines the degree of promising user. It may be predicted as “high”. Note that the above is an example, and the prediction apparatus 100 may predict the promising degree of the user by determining whether the user's action corresponds to various promising conditions.

[3. Configuration of prediction device]
Next, the configuration of the prediction apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 4 is a diagram illustrating a configuration example of the prediction device according to the embodiment. As illustrated in FIG. 4, the prediction device 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The prediction device 100 includes an input unit (for example, a keyboard and a mouse) that receives various operations from an administrator of the prediction device 100, and a display unit (for example, a liquid crystal display) for displaying various types of information. May be.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to the network by wire or wireless, and transmits / receives information to / from the terminal device 10.

(Storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As illustrated in FIG. 4, the storage unit 120 according to the embodiment includes a learning data storage unit 121, a model information storage unit 122, a user information storage unit 123, a promising degree information storage unit 124, and a prediction information storage unit 125. And have.

(Learning data storage unit 121)
The learning data storage unit 121 according to the embodiment stores various types of information related to learning data. FIG. 5 is a diagram illustrating an example of a learning data storage unit according to the embodiment. For example, the learning data storage unit 121 stores teacher data used for generating a model. The learning data storage unit 121 illustrated in FIG. 5 includes items such as “data ID”, “user ID”, “correct information”, and “behavior information”.

  “Data ID” indicates identification information for identifying data. For example, “data ID” indicates identification information for identifying a combination of user behavior information and correct information used as learning data (teacher data). For example, the data identified by the data ID “DT101” corresponds to the data DT101 shown in the example of FIG. “User ID” indicates identification information for identifying a user who is an action subject.

  “Correct answer information” indicates correct information corresponding to data identified by the data ID. For example, “correct answer information” indicates a user's job title corresponding to the data identified by the data ID and a score corresponding to the job title. FIG. 5 shows an example in which conceptual information such as “RDT101” is stored in “correct answer information”, but in reality, information indicating the user's job title and the score corresponding to the job title (for example, job title A or score “ 1 ") or a file path name indicating the storage location.

  “Behavior information” indicates behavior information including a history of user behavior corresponding to data identified by the data ID. FIG. 5 shows an example in which conceptual information such as “ADT101” is stored in “behavior information”, but in practice, various information related to actions performed by the user, or a file path name indicating the storage location. Etc. are stored.

  For example, in the “behavior information”, behavior information including a history of actions on the Internet (web) of the user who is the action subject is stored. For example, “behavior information” stores behavior information including a search history indicating what search query the user has used for the search. For example, “behavior information” stores behavior information including a purchase history indicating what kind of products the user has purchased. Further, for example, in “behavior information”, behavior information including a browsing history indicating what content the user has browsed is stored. The above is an example, and “behavior information” stores a history of various actions of the action subject.

  For example, in the example illustrated in FIG. 5, the data (data DT101) identified by the data ID “DT101” is information (data) corresponding to the user (user U101) identified by the user ID “U101”. Show. For example, in the example illustrated in FIG. 5, the data DT101 indicates that the behavior information ADT101 corresponding to the user U101 is included. Further, the data DT101 indicates that the correct answer information RDT101 is included.

  Note that the learning data storage unit 121 is not limited to the above, and may store various information according to the purpose. For example, the learning data storage unit 121 may store information related to the date and time when learning data was added. Further, for example, the learning data storage unit 121 may store information on user attributes when user attribute information is used for model input. For example, the learning data storage unit 121 may store demographic attribute information and psychographic attribute information as attribute information. For example, the learning data storage unit 121 may store information such as name, age, sex, home, work place, hobbies, interests, family structure, income, friendship, friendship, lifestyle, and the like.

  In the example illustrated in FIG. 5, the learning data used for generating the model M1 of the prediction target “position” is stored in the learning data storage unit 121. However, the learning data storage unit 121 stores each prediction target. Learning data corresponding to is stored. For example, the learning data storage unit 121 may store learning data in which a plurality of pieces of correct information corresponding to each prediction target are associated with each user's behavior information. For example, in addition to the correct information RDT101 of the prediction target “position”, correct information (correct information RDT201) of the prediction target “entrepreneur” may be associated with the behavior information ADT101 of the user U101. For example, the prediction device 100 generates a model M2 corresponding to the prediction target “entrepreneur” using the behavior information ADT101 and correct answer information RDT201 of the user U101. In the example illustrated in FIG. 5, the learning data storage unit 121 stores the user behavior information as learning data. However, the learning data storage unit 121 is not limited to the user behavior information, and includes various types of corporations and the like. The action information of the action subject may be stored as learning data. For example, the prediction device 100 generates a model M3 corresponding to the prediction target “achievement” using the corporate behavior information and the correct answer information corresponding to the prediction target “performance”.

(Model information storage unit 122)
The model information storage unit 122 according to the embodiment stores information related to the model. For example, the model information storage unit 122 stores model information (model data) generated by the generation process. FIG. 6 is a diagram illustrating an example of the model information storage unit according to the embodiment. The model information storage unit 122 illustrated in FIG. 6 includes items such as “action subject”, “model ID”, “prediction target”, and “model data”. In FIG. 6, only the models M1 to M3 are illustrated, but a large number of model information such as M4 and M5 may be stored according to each prediction target.

  Further, each model may be assumed to be used as a program module that is a part of the artificial intelligence software. For example, the model M1 may be assumed to be used as a program module that predicts the prediction target “position”. For example, the model data MDT1 may be data used as a program module for predicting the prediction target “position”. For example, the model M1 causes the computer to function so as to output a value obtained by quantifying the promising degree of the user based on the user behavior information.

  The “action subject” indicates an action subject whose promising degree is predicted. “Model ID” indicates identification information for identifying a model. For example, the model identified by the model ID “M1” corresponds to the model M1 illustrated in the example of FIG. “Prediction target” indicates a target for which the corresponding model predicts the promising degree. “Model data” indicates data of a corresponding model associated with the model data. For example, “model data” includes information including nodes in each layer, functions adopted by the nodes, connection relationships between the nodes, and connection coefficients set for connections between the nodes.

  For example, in the example shown in FIG. 6, the model (model M1) identified by the model ID “M1” and the model identified by the model ID “M2” (model M2) are subject to a user (natural person) Indicates that For example, in the example illustrated in FIG. 6, the model (model M3) identified by the model ID “M3” indicates that the target action subject is a corporation.

  For example, in the example illustrated in FIG. 6, the model M <b> 1 has the prediction target “position (promotion potential)” and the degree of promising degree of the user's position, that is, how much the user is based on the input user behavior information. It shows that it is used for predicting the degree of prospect of promotion (promotion degree of promotion). The model data of the model M1 is model data MDT1.

  The model M1 (model data MDT1) belongs to any layer other than the output layer, which is any of the input layer, the output layer, and the input layer to the output layer to which the action information of the user (action subject) is input. A first element and a second element whose value is calculated based on the first element and the weight of the first element, and for the action information of the user (action subject) input to the input layer, the output layer By using each element belonging to each layer other than the first element as a first element and performing a calculation based on the first element and the weight of the first element, the score value used for predicting the promising degree of the user (action subject) is output to the output layer This is a model for making a computer function so that it can output from the computer.

  Here, it is assumed that the models M1 to M3 are realized by a regression model represented by “y = a1 * x1 + a2 * x2 +... + Ai * xi”. In this case, for example, the first element included in the model M1 corresponds to input data (xi) such as x1 or x2. The weight of the first element corresponds to the coefficient ai corresponding to xi. Here, the regression model can be regarded as a simple perceptron having an input layer and an output layer. When each model is regarded as a simple perceptron, the first element can correspond to any node of the input layer, and the second element can be regarded as a node of the output layer.

  Further, it is assumed that the models M1 to M3 and the like are realized by a neural network having one or more intermediate layers such as DNN. In this case, for example, the first element included in the model M1 corresponds to any node of the input layer or the intermediate layer. The second element corresponds to the next node, which is a node to which a value is transmitted from the node corresponding to the first element. The weight of the first element corresponds to a connection coefficient that is a weight considered for a value transmitted from a node corresponding to the first element to a node corresponding to the second element.

  The model information storage unit 122 is not limited to the above, and may store various model information according to the purpose.

(User information storage unit 123)
The user information storage unit 123 according to the embodiment stores various types of information regarding the user. FIG. 7 is a diagram illustrating an example of a user information storage unit according to the embodiment. For example, the user information storage unit 123 stores various behavior information of each user. The user information storage unit 123 illustrated in FIG. 7 includes items such as “user ID” and “behavior information”.

  “User ID” indicates identification information for identifying a user. For example, the user identified by the user ID “U1” corresponds to the user U1 illustrated in the example of FIG. “Behavior information” indicates behavior information that is a history of user behavior corresponding to the data identified by the data ID.

  “Behavior information” indicates behavior information including a history of user behavior corresponding to data identified by the data ID. FIG. 5 shows an example in which conceptual information such as “ADT1” is stored in the “behavior information”, but in actuality, various information related to actions performed by the user, or a file path name indicating the storage location. Etc. are stored.

  For example, in the “behavior information”, behavior information including a history of actions on the Internet (web) of the user who is the action subject is stored. For example, “behavior information” stores behavior information including a search history indicating what search query the user has used for the search. For example, “behavior information” stores behavior information including a purchase history indicating what kind of products the user has purchased. Further, for example, in “behavior information”, behavior information including a browsing history indicating what content the user has browsed is stored. The above is an example, and “behavior information” stores a history of various actions of the action subject.

  For example, in the example illustrated in FIG. 7, the behavior information corresponding to the user (user U1) identified by the user ID “U1” includes a history of various behaviors such as search, content browsing, and purchase performed by the user U1. It shows that it is action information ADT1. Further, for example, in the example illustrated in FIG. 7, the behavior information corresponding to the user (user U2) identified by the user ID “U2” is a history of various behaviors such as search, content browsing, and purchase performed by the user U2. It shows that it is action information ADT2 containing.

  Note that the user information storage unit 123 is not limited to the above, and may store various types of information according to the purpose. Moreover, although the case where action information was memorize | stored in the user information storage part 123 for every user ID was shown in FIG. 7, action information may be memorize | stored not only for every user ID but for example in order of time.

  Note that the user information storage unit 123 is not limited to the above, and may store various types of information according to the purpose. For example, the user information storage unit 123 may store information related to user attributes (attribute information) as user information. For example, the user information storage unit 123 may store demographic attribute information and psychographic attribute information as attribute information. For example, the user information storage unit 123 may store information such as name, age, gender, home, work place, hobby, interest, family structure, income, friendship, friendship, lifestyle, etc. as attribute information. Good.

(Promising information storage unit 124)
The promising degree information storage unit 124 according to the embodiment stores various kinds of information related to the promising degree. FIG. 8 is a diagram illustrating an example of the promising degree information storage unit according to the embodiment. For example, the promising degree information storage unit 124 stores information indicating the correspondence between the score and the promising degree. The promising degree information storage unit 124 illustrated in FIG. 8 includes items such as “score” and “promising degree”.

  The “score” indicates a score value (range) corresponding to the corresponding promising degree. “Promising degree” indicates the level of the promising degree of the action subject when the score of the action subject is a corresponding score. The example of FIG. 8 shows a case where the “promising degree” has three levels of “low”, “medium”, and “high” corresponding to three score ranges.

  For example, in the example shown in FIG. 8, when the score of the action subject is less than 0.3, it indicates that the promising degree of the action subject is “low”. If the score of the action subject is 0.3 or more and less than 0.6, it indicates that the promising degree of the action subject is “medium”. In addition, when the score of the action subject is 0.6 or more, it indicates that the promising degree of the action subject is “high”.

  The promising degree information storage unit 124 is not limited to the above, and various information may be stored according to the purpose. For example, the promising degree information storage unit 124 may store information indicating the correspondence between the score and the promising degree for each prediction target.

(Prediction information storage unit 125)
The prediction information storage unit 125 according to the embodiment stores various types of information related to prediction. FIG. 9 is a diagram illustrating an example of the prediction information storage unit according to the embodiment. For example, the prediction information storage unit 125 stores various types of information related to the promising degree of the predicted action subject. The prediction information storage unit 125 illustrated in FIG. 9 includes items such as “acting subject”, “ID”, “prediction target”, “score”, “prediction rank”, and “promising degree”.

  The “action subject” indicates an action subject whose promising degree is predicted. “ID” indicates identification information for identifying an action subject such as a user or a corporation. For example, the action subject (user) identified by the ID “U1” corresponds to the user U1 illustrated in the example of FIG. “Prediction target” indicates a target for predicting the degree of promising. “Score” indicates the score of the corresponding prediction target for the corresponding action subject. The “predicted rank” indicates a rank predicted for the corresponding action subject based on the score of the corresponding prediction target. The “promising degree” indicates the promising degree predicted for the corresponding action subject based on the score of the corresponding prediction target.

  For example, in the example shown in FIG. 9, the user U1 who is a user (natural person) identified by the user ID “U1” has a score “0.7” for the prediction target “position (promotion potential)”. Indicates. The user U1 indicates that the prediction target “title (promotion potential)” is a predicted rank “director or higher”, that is, a user who is predicted to be promoted to a director or higher. In addition, the user U1 indicates that the prediction target “position (promotion potential for promotion)” is “high”, that is, the position is a user with a high degree of prospect for the position.

  Note that the prediction information storage unit 125 is not limited to the above, and may store various information according to the purpose.

(Control unit 130)
Returning to the description of FIG. 4, the control unit 130 is a controller and is stored in a storage device inside the prediction device 100 by, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. Various programs (corresponding to an example of a prediction program) are implemented by using the RAM as a work area. The control unit 130 is a controller, and is realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA). The control unit 130 includes an input layer, an output layer, and an input layer to an output layer to which the action information of the action subject is input by information processing according to the model M1 or the like stored in the model information storage unit 122. A first element belonging to a layer other than the output layer, and a second element whose value is calculated based on the first element and the weight of the first element, and is input to the input layer For each piece of behavior information, each element belonging to each layer other than the output layer is used as a first element, and the calculation based on the first element and the weight of the first element is performed. Output the value from the output layer.

  As illustrated in FIG. 4, the control unit 130 includes an acquisition unit 131, a generation unit 132, a prediction unit 133, and a provision unit 134, and realizes or executes information processing functions and operations described below. . Note that the internal configuration of the control unit 130 is not limited to the configuration illustrated in FIG. 4, and may be another configuration as long as the information processing described below is performed. The control unit 130, by information processing according to the model M1 (model data MDT1) stored in the storage unit 120, a second element whose value is calculated based on the first element and the weight of the first element, By performing an operation based on the first element and the weight of the first element with each element belonging to each layer other than the output layer as the first element for the user behavior information input to the input layer The score value used to predict the promising degree of the subject is output from the output layer.

(Acquisition part 131)
The acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires various types of information from the learning data storage unit 121, the model information storage unit 122, the user information storage unit 123, the promising degree information storage unit 124, the prediction information storage unit 125, and the like. The acquisition unit 131 may acquire various types of information from an external information processing apparatus. The acquisition unit 131 may acquire various types of information from the terminal device 10 or the like. For example, the acquisition unit 131 acquires user behavior information from the terminal device 10 used by the user. For example, the acquisition unit 131 may acquire user behavior information from another information processing apparatus that collects user behavior information.

  The acquisition unit 131 acquires action information indicating a history of actions by a predetermined action subject. The acquisition unit 131 acquires a model that outputs a score indicating the degree of promisingness of a predetermined action subject in response to input of action information of the predetermined action subject. The acquisition unit 131 acquires action information of a predetermined action subject who is a user. The acquisition unit 131 acquires behavior information including a history of user behavior on the Internet. The acquisition unit 131 acquires behavior information including a search history by the user.

  The acquisition unit 131 acquires behavior information including a purchase history by the user. The acquisition unit 131 acquires action information of actions by a predetermined action subject that is a predetermined group. The acquisition unit 131 acquires action information of actions by a predetermined action subject that is a predetermined corporation.

  For example, the acquisition unit 131 acquires user information including user attribute information. For example, the acquisition unit 131 acquires user information including information indicating a user's sex, age, and the like. For example, the acquisition unit 131 acquires user information including information indicating demographic attribute information and psychographic attribute information. For example, the acquisition unit 131 acquires user information including information indicating a name, age, sex, home, work place, hobbies, interests, family structure, income, friendship such as friendship, lifestyle, and the like.

In the example of FIG. 1, the acquisition unit 131 acquires the behavior information of each user U101 to U104.
The acquisition unit 131 acquires the behavior information ADT101 from the terminal device 10 used by the user U101. The acquisition unit 131 acquires action information ADT101 including a history of various actions such as search, content browsing, and purchase by the user U101. The acquisition unit 131 acquires the behavior information ADT102 from the terminal device 10 used by the user U102. The acquisition unit 131 acquires action information ADT102 including a history of various actions such as search, content browsing, and purchase by the user U102. The acquisition unit 131 acquires the behavior information ATD103 from the terminal device 10 used by the user U103. The acquisition unit 131 acquires the behavior information ATD104 from the terminal device 10 used by the user U104.

  The acquisition unit 131 acquires the title of each user from a company or the like to which each user belongs. The acquisition unit 131 may acquire the correct information RDT101 to RDT104 of each user U101 to U104 from a company to which each user belongs, another information processing apparatus, or the like. Moreover, the prediction apparatus 100 may acquire action information of each user from an external device other than the terminal device 10 used by the user.

  For example, the acquisition unit 131 acquires behavior information ADT101 indicating a history of behavior of the user U101 from the terminal device 10 used by the user U101. For example, the acquisition unit 131 acquires behavior information ADT102 indicating a history of behavior of the user U102 from the terminal device 10 used by the user U102. For example, the acquisition unit 131 acquires behavior information ADT103 indicating the history of the behavior of the user U103 from the terminal device 10 used by the user U103. Further, for example, the acquisition unit 131 acquires behavior information ADT104 indicating the history of the behavior of the user U104 from the terminal device 10 used by the user U104.

  In the example of FIG. 1, the acquisition unit 131 acquires learning data LD1. For example, the acquisition unit 131 acquires learning data LD1 including data DT101 to DT104.

  In the example of FIG. 2, the acquisition unit 131 acquires the behavior information ADT1 of the user U1. The acquisition unit 131 acquires the behavior information ADT1 of the user U1 from the terminal device 10 used by the user U1. The acquisition unit 131 acquires action information ADT1 including a history of various actions such as search, content browsing, and purchase by the user U1. The acquisition unit 131 acquires the behavior information ADT1 of the user U1 up to year Z. The acquisition unit 131 acquires the behavior information ADT1 of the user U1 in the year Z. The acquisition unit 131 acquires the behavior information ADT1 of the user U1 in the year 2017, which is Z year. For example, the acquisition unit 131 compares the date and time (acquisition date and time) when each piece of behavior information was acquired (detected) from the user behavior information group and the target period (for example, 2017), and the acquisition date and time is the target. If included in the period, the behavior information is acquired as the behavior information to be acquired. The acquisition unit 131 acquires information that associates positions and scores as shown in the rank list RL11 from the storage unit 120.

(Generator 132)
The generation unit 132 generates various types of information. For example, the generation unit 132 generates a model as shown in the model information storage unit 122 using the learning data stored in the learning data storage unit 121. For example, the generation unit 132 generates a model used for predicting the promising degree of the action subject based on the learning data acquired by the acquisition unit 131. For example, the generation unit 132 generates a model used for predicting the promising degree of the action subject based on learning data including the action information of the user and correct information indicating the type of promising degree associated with the user. .

  For example, the generation unit 132 generates models M1 to M3 and stores the generated models M1 to M3 and the like in the model information storage unit 122. Note that the generation unit 132 may generate the models M1 to M3 and the like using any learning algorithm. For example, the generation unit 132 generates models M1 to M3 and the like using a learning algorithm such as a neural network, a support vector machine (SVM), clustering, and reinforcement learning. As an example, when the generation unit 132 generates models M1 to M3 and the like using a neural network, the models M1 to M3 and the like include an input layer including one or more neurons, an intermediate layer including one or more neurons, and one And an output layer including the above neurons.

  The generation unit 132 generates a model and stores the generated model in the model information storage unit 122. Specifically, the generation unit 132 is a first layer belonging to any layer other than the output layer, which is any one of the input layer, the output layer, and the input layer to the output layer to which the action information of the action subject is input. Each element belonging to each layer other than the output layer with respect to the behavior information input to the input layer. As a first element, a calculation is performed based on the first element and the weight of the first element, thereby generating a model that outputs a score value used for predicting the promising degree of the action subject from the output layer.

  For example, the generation unit 132 generates a model based on the learning data. For example, as illustrated in the model information storage unit 122, the generation unit 132 generates models M1 to M3 and the like. In the example of FIG. 1, the generation unit 132 generates a model M1 based on the learning data. For example, the generation unit 132 generates a model by a predetermined learning process using learning data. For example, the generation unit 132 generates a model by performing learning using the data DT101 to DT104 in the learning data storage unit 121 as learning data (teacher data).

  In the example of FIG. 1, the generation unit 132 generates a model using a feature amount related to user behavior information. The generation unit 132 generates a model using the feature amount related to the behavior information corresponding to the search by the user. The generation unit 132 generates a model using the feature amount related to the query used by the user for the search. In addition, the generation unit 132 generates a model using the feature amount related to the behavior information corresponding to the content browsing by the user. The generation unit 132 generates a model using the feature amount related to the content viewed by the user. Moreover, the production | generation part 132 produces | generates a model using the feature-value regarding the action information corresponding to the purchase by a user. The generation unit 132 generates a model using the feature amount related to the product or service purchased by the user.

  In the example of FIG. 1, the generation unit 132 learns features corresponding to the user's behavior and generates a model that predicts the promising degree of the user who is the behavior subject. The generation unit 132 learns features related to user behavior information and generates a model that predicts the promising degree of the behavior subject.

  The generation unit 132 generates a model M1 using the learning data LD1. Since the position of the user U101 included in the correct information RDT101 is the position A (director) and the score is “1”, the generation unit 132 receives the user action information ADT101 included in the data DT101 in the model M1. In this case, the learning process is performed so that the score output from the model M1 approaches “1”. When the behavior information ADT101 of the data DT101 is input to the model M1, the generation unit 132 performs a learning process so that the score output by the model M1 approaches “1”.

  The generation unit 132 also inputs the user action information ADT102 included in the data DT102 to the model M1 because the position of the user U102 included in the correct answer information RDT102 is the D position (none) and the score is “0”. In such a case, the learning process is performed so that the score output from the model M1 approaches “0”. When the behavior information ADT102 of the data DT102 is input to the model M1, the generation unit 132 performs a learning process so that the score output from the model M1 approaches “0”.

  Further, since the position of the user U103 included in the correct information RDT103 is the C position (section manager) and the score is “0.3”, the generation unit 132 includes the behavior information ADT103 of the user included in the data DT103 in the model M1. Is input, the learning process is performed so that the score output by the model M1 approaches “0.3”. When the behavior information ADT103 of the data DT103 is input to the model M1, the generation unit 132 performs a learning process so that the score output by the model M1 approaches “0.3”.

  Further, the generation unit 132 has the position of the user U104 included in the correct information RDT104 as the position B (director) and the score is “0.6”. Is input so that the score output by the model M1 approaches “0.6”. When the behavior information ADT104 of the data DT104 is input to the model M1, the generation unit 132 performs a learning process so that the score output by the model M1 approaches “0.6”.

  In the example of FIG. 2, the generation unit 132 generates (calculates) a score indicating the promising degree of the prediction target “position” of the user U <b> 1 by processing as illustrated in the processing group PS <b> 22-1. The generation unit 132 generates the prediction information PL11 based on the prediction of the promising degree of the user U1.

(Prediction unit 133)
The prediction unit 133 predicts various types of information. The prediction unit 133 uses the information stored in the storage unit 120 to predict various information. The prediction unit 133 uses various information stored in the learning data storage unit 121, the model information storage unit 122, the user information storage unit 123, the promising information storage unit 124, the prediction information storage unit 125, and the like. Predict information. For example, the prediction unit 133 predicts various types of information based on various types of information acquired by the acquisition unit 131. The prediction unit 133 inputs action information (input data) of an action subject such as a user or a corporation to an input layer of the model by information processing according to a model such as the model M1. And the prediction part 133 outputs the score which shows the promising degree of an action subject from an output layer by propagating input data to an intermediate | middle layer and an output layer.

  Based on the behavior information acquired by the acquisition unit 131, the prediction unit 133 predicts the promising degree regarding the future of the predetermined behavior subject at a time point after the behavior. The prediction unit 133 inputs behavior information to the model, and predicts the promising degree of a predetermined behavior subject based on the score output by the model. The prediction unit 133 predicts the promising degree of a user who is a human (natural person) using the action information of a predetermined action subject who is a user.

  The prediction unit 133 appropriately predicts the promising degree of the user using the behavior information including the history of the user's behavior on the Internet. The prediction unit 133 predicts the degree of promising user using behavior information including a search history by the user. The prediction unit 133 predicts the user's promising degree using the behavior information including the purchase history by the user.

  The prediction unit 133 predicts the promising degree regarding the user's job title. The prediction unit 133 predicts the promising degree related to the user's position, and predicts whether the user is promoted in an organization such as a company. The predicting unit 133 predicts the promising degree of the user by comparing and determining which importance level of the correspondence table the score output by the model corresponds to using the correspondence table of the score and the promising degree.

  The prediction unit 133 predicts the promising degree of the predetermined group using the action information of the action by the predetermined action subject that is the predetermined group. The prediction unit 133 predicts the promising degree of a predetermined group such as an organization configured by a plurality of user groups. The prediction unit 133 predicts the promising degree of the predetermined corporation using the behavior information of the action by the predetermined action subject that is the predetermined corporation. The prediction unit 133 predicts the promising degree of a predetermined corporation that is an action subject having a legal personality.

  Further, for example, the prediction unit 133 may predict the user's promising degree using user information including the user's attribute information. For example, the prediction unit 133 may predict the promising degree of the user by using user information including information indicating the user's sex and age. For example, the prediction unit 133 may predict the promising degree of the user using demographic attribute information or psychographic attribute information. For example, the prediction unit 133 predicts the promising degree of the user using information indicating name, age, gender, home, place of work, hobby, interest, family structure, income, friendship, friendship, lifestyle, and the like. May be.

  For example, the prediction unit 133 predicts the promising degree of the position of the user U1 in 2022 five years from 2017 using the behavior information ADT1 and the model M1 of the user U1 in the year 2017. The prediction unit 133 inputs the behavior information ADT1 to the model M1. For example, the prediction unit 133 compares the date and time (acquisition date and time) when each piece of behavior information was acquired (detected) with the target period (for example, 2017) from the user U1 behavior information group, and the acquisition date and time is the target. If it is included in the period, the behavior information is extracted as the behavior information to be acquired. Then, the prediction unit 133 uses the extracted behavior information as information (behavior information ADT1) input to the model M1.

  In the example of FIG. 2, the prediction unit 133 generates (calculates) a score indicating the promising degree of the prediction target “position” of the user U <b> 1 by processing as illustrated in the processing group PS <b> 22-1. The prediction unit 133 inputs the action information of the user U1 who is the action subject to the model M1 corresponding to the prediction target “position (promotion degree of promotion)”. Specifically, the prediction unit 133 inputs the behavior information ADT1 to the model M1. The model M1 to which the behavior information ADT1 is input outputs a score. In the example of FIG. 2, the model M1 to which the behavior information ADT1 is input outputs a score “0.7” as indicated by the score SC11-1.

  In the example of FIG. 2, the predicting unit 133 predicts the promising degree of the user U1 based on the score output by the model M1. For example, the prediction unit 133 generates the prediction information PL11 based on the prediction of the promising degree of the user U1. The prediction unit 133 predicts the promising degree of the user U1 based on the score output from the model M1 and the information stored in the promising degree information storage unit 124. The predicting unit 133 predicts the promising degree of the user U1 based on information (associating information) in which the score and the promising degree are associated with each other as shown in the promising degree information storage unit 124 in FIG.

  The predicting unit 133 compares the score output by the model M1 with the score range of the association information in the promising degree information storage unit 124 illustrated in FIG. 2, and the score output by the model M1 is in any score range. Determine whether it is included. In the example of FIG. 2, the predicting unit 133 determines that the score output by the model M1 is “0.7”, and the promising degree corresponds to a score “0.6 or more” corresponding to “high”. Therefore, as shown in the prediction information PL11, the predicting unit 133 predicts that the promising degree corresponding to the prediction target “post (promotion potential)” of the user U1 is “high”.

  In the example of FIG. 2, the prediction unit 133 predicts the post of the user U1 after year Y from year Z using the rank list RL11. The prediction unit 133 compares the score output by the model M1 with the score of the promotion information in the rank list RL11 illustrated in FIG. 2, and determines which score is higher than the score output by the model M1. In the example of FIG. 2, the prediction unit 133 has a score output by the model M1 of “0.7”, a score of “B” (director) or more than “0.6”, and a score of “A” (director) “ It is determined that it is less than 1 ”. Therefore, as shown in the prediction information PL11, the prediction unit 133 predicts the position of the user U1 in the prediction target “position (promotion degree of promotion)” as “director or higher”. For example, the predicting unit 133 predicts the post of the user U1 Y years after the Z year as “director or higher”. In this case, the prediction unit 133 predicts that the user U1 is promoted to a position higher than the general manager after year Y from year Z. For example, the prediction unit 133 predicts that the user U1 is promoted to a position higher than the general manager in 2022, five years after 2017.

  For example, the prediction unit 133 calculates a score using a model having an arbitrary structure such as the above-described regression model or neural network. Specifically, the model M1 is a value obtained by quantifying the prediction of a predetermined target (that is, the action subject's action) when the user's action information (that is, each element used for calculating the above-described score) is input. A coefficient is set so as to output a score that suggests whether the degree of promise regarding the prediction target is high. The prediction unit 133 calculates a score related to the promising degree of the action subject using such a model M1.

  In the above example, the model M1 is an example of a model that outputs a value obtained by quantifying the prediction of the promising degree of the action subject when the action information of the user is input. However, the model (model X) according to the embodiment may be a model generated based on a result obtained by repeatedly inputting / outputting data to / from the model M1. For example, the model X may be a model (model Y) that has been learned so that user behavior information is input and the score output by the model M1 is output. Alternatively, the model M1 may be a model that has been learned so that user behavior information is input and the output value of the model Y is output. When the prediction unit 133 performs a prediction process using GAN (Generative Adversarial Networks), the model M1 may be a model that constitutes a part of the GAN.

(Providing unit 134)
The providing unit 134 provides various information. For example, the providing unit 134 provides various information to the terminal device 10. For example, the providing unit 134 provides a service related to the promising degree of the action subject predicted by the prediction unit 133. For example, the providing unit 134 provides the user with information regarding the promising degree of the action subject predicted by the prediction unit 133. For example, the providing unit 134 provides information regarding the promising degree of the action subject predicted by the prediction unit 133 to the terminal device 10 used by the user. Further, for example, the providing unit 134 may provide information regarding the model generated by the generating unit 132 to an external information processing apparatus. For example, the providing unit 134 may provide information output from the model to an external information processing apparatus.

  For example, the providing unit 134 provides information based on the predicted promising degree of the action subject. In the example of FIG. 2, the providing unit 134 provides the prediction information PL <b> 11 of the user U <b> 1 to a company that desires information regarding the degree of promising user U <b> 1. The providing unit 134 provides the prediction information PL11 of the user U1 to the operator terminal 20 used by the manager MA1 of the company CP11 that the user U1 has undergone the employment test. The providing unit 134 transmits the prediction information PL11 of the user U1 to the business operator terminal 20 used by the manager MA1.

[4. Generation process flow)
Next, the procedure of the generation process by the prediction system 1 according to the embodiment will be described using FIG. FIG. 10 is a flowchart illustrating an example of the generation process according to the embodiment.

  As illustrated in FIG. 10, the prediction device 100 acquires learning data (step S101). For example, the prediction device 100 acquires learning data from the learning data storage unit 121.

  Thereafter, the prediction device 100 generates a model based on the learning data (step S102). In the example of FIG. 1, the prediction device 100 generates a model M1 and the like using learning data from the learning data storage unit 121.

[5. (Prediction process flow)
Next, the procedure of the generation process by the prediction system 1 according to the embodiment will be described with reference to FIG. FIG. 11 is a flowchart illustrating an example of the prediction process according to the embodiment.

  As illustrated in FIG. 11, the prediction device 100 acquires user behavior information (step S <b> 201). In the example of FIG. 2, the prediction device 100 acquires the behavior information ADT1 of the user U1.

  Also, the prediction device 100 predicts the promising degree of the action subject using the user action information and the model (step S202). In the example of FIG. 2, the prediction device 100 predicts the promising degree regarding the position of the user U1 based on the score output by the model M1.

  Further, the prediction device 100 provides information on the predicted degree of promising user (step S203). In the example of FIG. 2, the prediction device 100 provides the prediction information PL11 to the operator terminal 20 used by the administrator MA1 of the company CP11 for which the user U1 has undergone the employment test.

[6. effect〕
As described above, the prediction device 100 according to the embodiment includes the acquisition unit 131 and the prediction unit 133. The acquisition unit 131 acquires action information indicating a history of actions by a predetermined action subject. In addition, the prediction unit 133 predicts the promising degree regarding the future of the predetermined action subject at a time point after the action based on the action information acquired by the acquisition unit 131.

  As described above, the prediction device 100 according to the embodiment predicts the promising degree regarding the future of the predetermined action subject at a time point after the action based on the action information indicating the history of the action by the predetermined action subject. Thus, the promising degree of the action subject can be appropriately predicted.

  Further, in the prediction device 100 according to the embodiment, the acquisition unit 131 acquires a model that outputs a score indicating the degree of promising behavior of a predetermined behavior subject in response to input of behavior information of the predetermined behavior subject. The prediction unit 133 inputs behavior information to the model, and predicts the promising degree of a predetermined behavior subject based on the score output by the model.

  As described above, the prediction device 100 according to the embodiment inputs behavior information to a model that outputs a score indicating the degree of promising behavior of a predetermined behavior subject in response to the input of behavior information of the predetermined behavior subject, and the model outputs By predicting the promising degree of a predetermined action subject based on the score, the promising degree of the action subject can be appropriately predicted.

  In the prediction device 100 according to the embodiment, the acquisition unit 131 acquires action information of a predetermined action subject who is a user.

  As described above, the prediction device 100 according to the embodiment appropriately acquires the promising degree of the user who is a human (natural person) by acquiring the action information of the predetermined action subject who is the user and predicting the promising degree of the user. Can be predicted.

  In the prediction device 100 according to the embodiment, the acquisition unit 131 acquires behavior information including a history of user behavior on the Internet.

  As described above, the prediction device 100 according to the embodiment appropriately sets the promising degree of the user who is a human (natural person) by predicting the promising degree of the user by using the behavior information including the history of the behavior of the user on the Internet. Can be predicted.

  In the prediction device 100 according to the embodiment, the acquisition unit 131 acquires behavior information including a search history by the user.

  As described above, the prediction device 100 according to the embodiment appropriately predicts the promising degree of the user who is a human (natural person) by predicting the promising degree of the user by using the behavior information including the search history by the user. be able to.

  In the prediction device 100 according to the embodiment, the acquisition unit 131 acquires behavior information including a purchase history by the user.

  As described above, the prediction device 100 according to the embodiment appropriately predicts the promising degree of the user who is a human (natural person) by predicting the promising degree of the user by using the behavior information including the purchase history by the user. be able to.

  In the prediction device 100 according to the embodiment, the prediction unit 133 predicts the promising degree related to the user's post.

  Thus, since the prediction apparatus 100 according to the embodiment can predict whether or not the user is promoted in an organization such as a company by predicting the degree of promising user's job title, the user's promising degree is appropriately set. Can be predicted.

  Further, in the prediction device 100 according to the embodiment, the acquisition unit 131 acquires behavior information on behavior by a predetermined behavior subject that is a predetermined group.

  As described above, the prediction device 100 according to the embodiment acquires behavior information on behavior by a predetermined behavior subject that is a predetermined organization, and predicts the promising degree of the predetermined organization, for example, by a plurality of user groups or the like. The promising degree of a predetermined group such as a configured organization can be appropriately predicted.

  Moreover, in the prediction device 100 according to the embodiment, the acquisition unit 131 acquires behavior information on behavior by a predetermined behavior subject that is a predetermined corporation.

  As described above, the prediction device 100 according to the embodiment acquires behavioral information on behaviors by a predetermined behavioral entity that is a predetermined corporation, and predicts the promising degree of the predetermined corporateity, for example, by a behavioral entity having a legal personality. The promising degree of a certain corporation can be appropriately predicted.

[7. Hardware configuration)
The prediction apparatus 100 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in FIG. 12, for example. FIG. 12 is a hardware configuration diagram illustrating an example of a computer that realizes the function of the prediction device. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F). ) 1700.

  The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400 and controls each unit. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

  The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. The communication interface 1500 receives data from other devices via the network N and sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the network N.

  The CPU 1100 controls an output device such as a display and a printer and an input device such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input device via the input / output interface 1600. In addition, the CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  For example, when the computer 1000 functions as the prediction apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 performs control by executing a program or data (for example, model M1 (model data MDT1)) loaded on the RAM 1200. The function of the unit 130 is realized. The CPU 1100 of the computer 1000 reads and executes these programs or data (for example, model M1 (model data MDT1)) from the recording medium 1800. As another example, these programs or data are transmitted from other devices via the network N. May be obtained.

  As described above, some of the embodiments and modifications of the present application have been described in detail with reference to the drawings. However, these are mere examples, and various types based on the knowledge of those skilled in the art, including the aspects described in the disclosure line of the invention. It is possible to carry out the present invention in other forms that have been modified and improved.

[8. Others]
In addition, among the processes described in the above-described embodiments and modifications, all or a part of the processes described as being automatically performed can be manually performed, or are described as being performed manually. All or part of the processing can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the document and drawings can be arbitrarily changed unless otherwise specified. For example, the various types of information illustrated in each drawing is not limited to the illustrated information.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured.

  In addition, the above-described embodiments and modifications can be combined as appropriate within a range that does not contradict processing contents.

  In addition, the “section (module, unit)” described above can be read as “means” or “circuit”. For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

DESCRIPTION OF SYMBOLS 1 Prediction system 100 Prediction apparatus 121 Learning data storage part 122 Model information storage part 123 User information storage part 124 Promising degree information storage part 125 Prediction information storage part 130 Control part 131 Acquisition part 132 Generation part 133 Prediction part 134 Provision part 10 Terminal apparatus N network

Claims (12)

An acquisition unit that acquires action information indicating a history of actions by a predetermined action subject;
Based on the behavior information acquired by the acquisition unit, a prediction unit that predicts the promising degree related to the future of the predetermined behavior subject at a time point later than the behavior;
A prediction apparatus comprising: The acquisition unit
In response to the input of the action information of the predetermined action subject, obtain a model that outputs a score indicating the promising degree of the predetermined action subject,
The prediction unit
The prediction apparatus according to claim 1, wherein the behavior information is input to the model, and the promising degree of the predetermined behavior subject is predicted based on a score output by the model. The acquisition unit
The prediction apparatus according to claim 1, wherein the behavior information of the predetermined behavior subject that is a user is acquired. The acquisition unit
The prediction apparatus according to claim 3, wherein the behavior information including a history of the user's behavior on the Internet is acquired. The acquisition unit
The prediction apparatus according to claim 4, wherein the behavior information including a search history by the user is acquired. The acquisition unit
The prediction device according to claim 3, wherein the behavior information including a browsing history of content by the user is acquired. The acquisition unit
The prediction apparatus according to claim 3, wherein the behavior information including a purchase history by the user is acquired. The prediction unit
The prediction device according to claim 3, wherein the promising degree related to the user's post is predicted. The acquisition unit
The prediction apparatus according to claim 1, wherein action information of an action by the predetermined action subject that is a predetermined group is acquired. The acquisition unit
The prediction apparatus according to claim 9, wherein action information of an action by the predetermined action subject that is a predetermined corporation is acquired. A prediction method performed by a computer,
An acquisition step of acquiring behavior information indicating a history of behavior by a predetermined behavior subject;
Based on the behavior information acquired by the acquisition step, a prediction step of predicting the promising degree related to the future of the predetermined behavior subject at a time point later than the behavior;
The prediction method characterized by including. An acquisition procedure for acquiring behavior information indicating a history of behavior by a predetermined behavior subject;
Based on the behavior information acquired by the acquisition procedure, a prediction procedure for predicting the promising degree related to the future of the predetermined behavior subject at a time point later than the behavior;
A prediction program that causes a computer to execute.

Images